Delay Prediction of Aircrafts Based on Health Monitoring Data

Flight delay is a major issue faced by airline companies. Delay in the aircraft take off can lead to penalty and extra payment to airport authorities leading to revenue loss. The causes for delays can be weather, traffic queues or component issues. In this paper, we focus on the problem of delays due to component issues in the aircraft. In particular, this paper explores the analysis of aircraft delays based on health monitoring data from the aircraft. This paper analyzes and establishes the relationship between health monitoring data and the delay of the aircrafts using exploratory analytics, stochastic approaches and machine learning techniques.

Perspective: The Exponential Learning Curve of Analytics

N.A.

Case Study: Text-Mining Customers View Point and Perceived Value About Brand

paper describes how text mining techniques can be applied in the analysis of consumer voice to gain useful and actionable business insights for marketers. The technique is illustrated via its application to understand Brands perceived value of certain automobile brands. This case study shows the use of text mining techniques to understand brands perception vis-a-vis competition from their opinion, sentiment and reactions. As the amount of online text increases, the demand for text classification to aid the analysis and management of text is increasing. Data acquisition in this case is not costly, information is rich in nature, classification of text can provide this information at low cost, but the classifiers themselves must be built with expensive human effort, or trained from texts which have themselves been manually classified. In this paper, we mention about a procedure of classifying text using the concept of association rule of data mining and correspondence analysis for Brand perception.

Claim Analytics across Multiple Insurance Lines of Business

Claim loss payouts attribute most significantly to the overall costs of any insurance company and subsequently have a greater impact on its profits. Settling claims early, detecting fraudulent claims, increasing customer satisfaction and customer retention through recurring business have become increasingly important. The key to gain competitive edge is the ability to quickly and efficiently explore and understand data, settle claims and enhance customer experience. Claims processing, for any line of business in insurance (i.e. auto, life or health) is time consuming and labor-intensive involving multiple systems and several business units. To address the above challenges and support the claim handlers decision, information that is available during the first notification of loss (FNOL) is used to predict claim severity using predictive analytics. A claim that is straight forward with reliable evidences can be considered as a simple claim which can be settled quickly and dealt by a junior adjustor. While a claim which involves accident, death or a police case can be considered as complex and needs a team of senior adjustors or lawyers to get involved. Using the prediction model, the claims department can classify the claims based on its severity and assign it to the respective team thus improving its operations. Additionally the research also involves analysis of similarities and differences between the key attributes across three lines of business in insurance (auto, life and health) that impact the claims severity. By further studying the claim trends across these lines of business for a particular geography or demography, business can further refine the risks considered during underwriting or can design new products with add-ons which will be beneficial to the customers and contribute to increased business.

Airline Revenue Management Revenue Maximization through Corporate Channel

This paper explains an empirical model that has been developed to arrive at the Best Possible Fare (BPF) for all the ad-hoc requests made by the corporate passengers. For the purpose of this research, a corporate request is considered ad-hoc if the booking request is initiated after the corporate channel for the particular flight is closed. By charging the best possible fare, the airline will be able to marginally increase its revenue without deviating from the guidelines of the corporate channel. This model updates itself with the available capacity at the time when the ad-hoc request is initiated, also considers the previous booking data to forecast the passenger demand and the channel behavior. This will lessen the manual intervention and its associated errors, and will take care of the number of corporate requests that can be approved and size of the corporate booking requests that can be approved. As the factors affecting the booking trend of the airlines have been covered earlier in various research papers as discussed in the literature review, we have directly focused on deriving the empirical solution in this paper.

Is Your New Product Really Boosting our Sales? An Econometric Model to Quantify the Cannibalization Effect

N.A.

Forecasting The Stock Market Values Using Hidden Markov Model

The financial market influences personal corporate financial lives and the economic health of a country. Price change of stock market is not a completely random model. The pattern of financial market has been observed by some economists, statisticians and computer scientists. This paper gives a detailed idea about the sequence and state prediction of stock market using Hidden Markov Model and also making inferences regarding stock market trend. The one day difference in close value of stock market value has been used for some period and the corresponding transition probability matrix and emission probability matrix are obtained. Seven optimal hidden states and three sequences are generated using MATLAB and then compared.

A Study on the Analytics Tool Used in Decision Making at Small and Medium Enterprise

The article focuses on the study of prevailing decision making styles of Small Scale Industrial (SSI) Units. It presents data collected from 200 SSI units from Bhavnagar – a coastal city of Gujarat, India. The objective of writing the article is to depict heuristic decision patterns of small and medium enterprises, and the rare use of analytical or statistical business intelligence tools in decision making processes. It would be interesting to study the design of decision taken on routine basis in small units, poorly equipped with technology and technical know-how. The paper is descriptive in terms, and lays a lucid picture of present decision making processes.

Analytics for Decision Making at Ports

Ports serve as an important link in global supply chain. Worldwide more than 75 percent of cargo move by sea. Over the years, the Indian Union has endeavoured to invest on major ports of the country to meet up to the global standards. Yet the share of major ports under the government of India has decrease from 90 to 70 percentage of total sea borne cargo in the country. The major ports lost its share to the minor ports under the state governments. Two reasons could be hypothesized for the said problem. One, the investments are not made in the right direction and other that the efficiency needs to be improved in functioning of the ports. In this paper an attempt has been made to identify the dimensions of port performance and the causality between the dimensions. It chooses to take average turn round time (ATRT) as an indicator of port performance. The paper proposes an analytical framework to identify the causality that would aid the decision makers. The causal approach has been based on identifying the dimensions (factors) using multi-variate data analysis, establishing the linear causal association between the ATRT and the factors, analyzing the relationship so obtained to propose an System Dynamics model for policy simulation by the decision makers.

Interval-valued Data Analysis

N. A.